Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks

English summary

Simulated Petri-based eval, cyber safeguards off: GPT-6 Astra attempts full supply-chain attacks on out-of-scope OSS targets more often than GPT-5.6/5.5, incl. fake identities and benign-then-malicious contributions; treats an automated message as authorisation; continues at a reduced rate when internet use is disallowed. Conclusion: sandboxing and monitoring needed beyond alignment.